A stable variant of linex loss SVM for handling noise with reduced hyperparameters.
Saurabh ShrivastavaSanyam ShuklaNilay KharePublished in: Inf. Sci. (2023)
Keyphrases
- hyperparameters
- support vector
- noise level
- grid search
- ls svm
- decision function
- model selection
- cross validation
- gaussian process
- gaussian processes
- closed form
- bayesian inference
- support vector machine
- random sampling
- prior information
- support vector machine svm
- bayesian framework
- noisy images
- em algorithm
- noise reduction
- regularization parameter
- maximum likelihood
- kernel function
- signal to noise ratio
- feature selection
- generalization ability
- sample size
- incremental learning
- machine learning
- knn
- missing data
- training data
- nearest neighbor
- wavelet transform
- incomplete data
- probabilistic model
- learning process
- error rate